metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: Mistral-PromptTuning-Weights-Binary-Hate-Speech-Detection
results: []
Mistral-PromptTuning-Weights-Binary-Hate-Speech-Detection
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4243
- Micro F1: 0.8033
- Macro F1: 0.7028
- Accuracy: 0.8033
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 5
Training results
Framework versions
- Transformers 4.36.1
- Pytorch 2.1.0+cu121
- Datasets 2.13.1
- Tokenizers 0.15.0
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.6.2